© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1735
    Prev
    Next
    INDEX
    Explanations

    words related to computer viruses and computer security

    oai_token-act-pair · gpt-3.5-turbo

    references to viruses and antivirus software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lif
    -0.70
     trad
    -0.67
     loft
    -0.65
     meetings
    -0.64
     flat
    -0.64
     mon
    -0.63
     specifically
    -0.63
     straight
    -0.63
     drawing
    -0.61
     stand
    -0.61
    POSITIVE LOGITS
    irus
    4.43
    iral
    2.08
     Virus
    1.25
     virus
    1.21
    culosis
    1.17
    unia
    1.12
    ir
    1.09
    irens
    1.08
    itamin
    1.08
    irin
    1.05
    Activations Density 0.010%

    No Known Activations